Related Experiment Video
Updated: Sep 26, 2025

Whole-body PET/MRI of Pediatric Patients: The Details That Matter
Published on: December 19, 2017
MRI Radiogenomics of Pediatric Medulloblastoma: A Multicenter Study
Michael Zhang1, Samuel W Wong1, Jason N Wright1
1From the Departments of Neurosurgery (M.Z., Q.Z.), Otolaryngology-Head and Neck Surgery (Q.Z.), and Pathology (S.S.A., H.V.), Stanford Hospital and Clinics, Stanford, Calif; Departments of Radiology (M.Z., K.W.Y.), Neurology (P.G.F.), and Neurosurgery (G.A.G.), Lucile Packard Children's Hospital, Stanford University, 725 Welch Rd, G516, Palo Alto, CA 94304; Department of Statistics, Stanford University, Stanford, Calif (S.W.W.); Department of Radiology (J.N.W.) and Division of Pediatric Hematology/Oncology, Department of Pediatrics (N.A.V.), Seattle Children's Hospital, Seattle, Wash; Department of Radiology, Harborview Medical Center, Seattle, Wash (J.N.W.); Departments of Diagnostic Imaging (M.W.W., S. Laughlin, B.E.W.) and Surgery (M.T.) and Division of Haematology/Oncology, Department of Pediatrics (V.R.), The Hospital for Sick Children, Toronto, Canada; Departments of Neurosurgery (S.T., K.A.), Radiology (K.M.), and Developmental Biology & Cancer (T.S.J.), Great Ormond Street Institute of Child Health, London, UK; Department of Pediatrics, Children's Hospital of Philadelphia, Philadelphia, Pa (M.H.); Stanford School of Medicine, Stanford University, Stanford, Calif (L.T.T.); Departments of Radiology (K.S., M.M.) and Neurosurgery (S.H.), Duke Children's Hospital & Health Center, Durham, NC; Department of Physiology and Nutrition, University of Colorado-Colorado Springs, Colorado Springs, Colo (S. Lummus); Department of Radiology, Children's Hospital of Orange County, Orange, Calif (H.L., A.E.); Department of Radiology, New York University Grossman School of Medicine, New York, NY (A.R.); Division of Pediatric Neurosurgery, Department of Neurosurgery, and Huntsman Cancer Institute, University of Utah School of Medicine, Intermountain Healthcare Primary Children's Hospital, Salt Lake City, Utah (J.N., S.H.C., E.T.); Division of Child Neurology, Department of Pediatrics, Centre Hospitalier Universitaire Sainte-Justine, Université de Montréal, Montreal, Canada (S. Perreault); Department of Clinical Radiology & Imaging Sciences, Riley Children's Hospital, Indianapolis, Ind (K.R.M.B., C.Y.H.); Division of Neurosurgery, Dayton Children's Hospital, Dayton, Ohio (R.M.L.); Department of Pediatrics, Doernbecher Children's Hospital, Portland, Ore (Y.J.C.); Department of Radiology, Boston Children's Hospital, Boston, Mass (T.P.); Department of Pediatrics, Hopp Children's Cancer Center, Heidelberg, Germany (S. Pfister); and Department of Medical Imaging, Ann & Robert H. Lurie Children's Hospital of Chicago, Chicago, Ill (A.J.).
Abstract:
Background Radiogenomics of pediatric medulloblastoma (MB) offers an opportunity for MB risk stratification, which may aid therapeutic decision making, family counseling, and selection of patient groups suitable for targeted genetic analysis. Purpose To develop machine learning strategies that identify the four clinically significant MB molecular subgroups. Materials and Methods In this retrospective study, consecutive pediatric patients with newly diagnosed MB at MRI at 12 international pediatric sites between July 1997 and May 2020 were identified. There were 1800 features extracted from T2- and contrast-enhanced T1-weighted preoperative MRI scans. A two-stage sequential classifier was designed-one that first identifies non-wingless (WNT) and non-sonic hedgehog (SHH) MB and then differentiates therapeutically relevant WNT from SHH. Further, a classifier that distinguishes high-risk group 3 from group 4 MB was developed. An independent, binary subgroup analysis was conducted to uncover radiomics features unique to infantile versus childhood SHH subgroups. The best-performing models from six candidate classifiers were selected, and performance was measured on holdout test sets. CIs were obtained by bootstrapping the test sets for 2000 random samples. Model accuracy score was compared with the no-information rate using the Wald test. Results The study cohort comprised 263 patients (mean age ± SD at diagnosis, 87 months ± 60; 166 boys). A two-stage classifier outperformed a single-stage multiclass classifier. The combined, sequential classifier achieved a microaveraged F1 score of 88% and a binary F1 score of 95% specifically for WNT. A group 3 versus group 4 classifier achieved an area under the receiver operating characteristic curve of 98%. Of the Image Biomarker Standardization Initiative features, texture and first-order intensity features were most contributory across the molecular subgroups. Conclusion An MRI-based machine learning decision path allowed identification of the four clinically relevant molecular pediatric medulloblastoma subgroups. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Chaudhary and Bapuraj in this issue.
Related Concept Videos
Imaging Studies IV: Magnetic Resonance Imaging
Radiological Investigation II: MRI and Ventilation Perfusion Scan
Magnetic Resonance Imaging (MRI) and Ventilation Perfusion Scans are two radiological investigations that offer detailed diagnostic images of the body, particularly lung structures.
MRI
MRI uses magnetic fields and radiofrequency signals to distinguish between normal and abnormal tissues. This technology provides a more detailed diagnostic image than CT scans, enabling it to characterize pulmonary nodules, stage bronchogenic carcinoma, and evaluate inflammatory activity in...
Magnetic Resonance Imaging

